Sciweavers

107 search results - page 20 / 22
» Uniqueness of simultaneous approximations in continuous func...
Sort
View
ICANN
2009
Springer
14 years 3 hour ago
An EM Based Training Algorithm for Recurrent Neural Networks
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...
Jan Unkelbach, Yi Sun, Jürgen Schmidhuber
ICML
2010
IEEE
13 years 8 months ago
Inverse Optimal Control with Linearly-Solvable MDPs
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
Dvijotham Krishnamurthy, Emanuel Todorov
MM
2010
ACM
169views Multimedia» more  MM 2010»
13 years 7 months ago
CO3 for ultra-fast and accurate interactive segmentation
This paper presents an interactive image segmentation framework which is ultra-fast and accurate. Our framework, termed "CO3", consists of three components: COupled repr...
Yibiao Zhao, Song Chun Zhu, Siwei Luo
TOG
2012
232views Communications» more  TOG 2012»
11 years 9 months ago
Discovery of complex behaviors through contact-invariant optimization
We present a motion synthesis framework capable of producing a wide variety of important human behaviors that have rarely been studied, including getting up from the ground, crawl...
Igor Mordatch, Emanuel Todorov, Zoran Popovic
COMPGEOM
2000
ACM
13 years 11 months ago
Fast computation of generalized Voronoi diagrams using graphics hardware
: We present a new approach for computing generalized Voronoi diagrams in two and three dimensions using interpolation-based polygon rasterization hardware. The input primitives ma...
Kenneth E. Hoff III, Tim Culver, John Keyser, Ming...